Q3 REPORT

The Frontier Model Landscape

This is our third edition of our quarterly report on the capabilities of generative AI models.

AI models/startups have now become ubiquitous with contemporary economic, technological, and social development. New model releases have become a central point of discourse in tech circles, and the race to AGI is continuously heating up. RL environments for specific use-cases have made a resurgence for frontier labs, who are now exclusively focused on frontier capabilities. Specific use-cases, in particular coding, have also become the focus of major AI labs. 

Download PDF or read the full report here 👇

Let’s Redefine AI Benchmarking Together

AI performance measurement needs precision, transparency, and reliability—that’s what we deliver. Whether you’re a researcher, developer, enterprise leader, or journalist, we’d love to connect.

Let’s Redefine AI Benchmarking Together

AI performance measurement needs precision, transparency, and reliability—that’s what we deliver. Whether you’re a researcher, developer, enterprise leader, or journalist, we’d love to connect.

Let’s Redefine AI Benchmarking Together

AI performance measurement needs precision, transparency, and reliability—that’s what we deliver. Whether you’re a researcher, developer, enterprise leader, or journalist, we’d love to connect.